HR & RECRUITING

Anonymize Take-Home Submissions on Dropbox Upload

Watches a Dropbox intake folder for new candidate take-home files, strips names and identifying metadata, assigns a blind code, and files the clean copy into a reviewer folder.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew file in Dropbox intake folderDropboxDropbox
  • ActionGenerate blind code and log name mapping in NotionNotionNotion
  • ActionStrip author metadata and name fragmentsOpenAI
  • ActionRename to blind code and upload to reviewer folderDropboxDropbox
  • OutputPost new candidate code to recruiting SlackSlack

What it does

Turns raw candidate take-home submissions into bias-free review packets the moment they land. When a candidate uploads their assignment to a Dropbox intake folder, this workflow generates an anonymous candidate code, removes personal identifiers from filenames and document metadata, and drops the scrubbed copy into a separate reviewer folder that hiring managers can open without ever seeing who wrote it.

When to use it

Use it when candidates submit take-home work directly to a shared Dropbox folder and you want every reviewer to evaluate the work blind. Ideal for engineering, design, or analyst hiring loops where the original filename (often a person's name) leaks identity before the work is even read.

How it works

  1. 1A new file in the Dropbox intake folder triggers the run.
  2. 2The workflow generates a unique blind code (e.g. CAND-7QF2) and records the real-name-to-code mapping in a private Notion table only recruiting can see.
  3. 3An OpenAI step scrubs author metadata and any name fragments from the document body.
  4. 4The cleaned file is renamed to the blind code and uploaded to the Dropbox reviewer folder.
  5. 5A confirmation message posts to the recruiting Slack channel with the new code.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect NotionPages, databases, comments.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.